
Unlock the potential of Reinforcement Learning (RL) in this fast-paced, 60-minute masterclass. Moving beyond traditional...
49 RSVP'd
Unlock the potential of Reinforcement Learning (RL) in this fast-paced, 60-minute masterclass. Moving beyond traditional data-crunching, Dr. Richard Zhao explores the world of "Learning by Doing." You will see how AI agents navigate complex environments, learn from trial and error, and solve problems that traditional programming cannot touch.
Key Takeaways:
The RL Advantage: Why "learning from rewards" is a game-changer for AI.
Agent Dynamics: A look at how AI mimics human trial-and-error.
Rapid Use Cases: Real-world applications in robotics, gaming, and optimization.
Accelerated 60-Minute Event Plan
To maximize the one-hour window, the session is designed to be lean, shifting quickly from theory to discussion.
Time
Segment
Focus
0:00 - 0:05
Quick Start
Opening by the TypeShift team; speaker introduction.
0:05 - 0:15
AI & ML Context
Brief overview of where RL fits in the broader AI landscape.
0:15 - 0:35
Core Presentation
Dr. Zhao on RL mechanics: Agents, Environments, and Rewards.
0:35 - 0:50
Applications & Why RL
Real-world examples and why this technology is trending now.
0:50 - 1:00
Rapid Q&A & Wrap
High-speed audience questions and closing feedback.
Thursday, April 23, 2026
12:00 AM – 1:00 AM (UTC)
University of Calgary
The Power of Reinforcement Learning
ᐳᐅ!DEVFESTYYC
Platforms
Technical Expert, Activation ᐳᐅ!DEVFESTYYC
AIRIA
Chapter Founder
GDG Organizer, People Experiences
atVenu
Director, Production ᐳᐅ!DEVFESTYYC
Director, Operations ᐳᐅ!DEVFESTYYC
The Adaptavist Group
GDG Organizer, Women Techmakers Ambassador